Publication: Cerebrovascular Segmentation Architecture With Channel Attention And Spatial Kernel Filtering For Tof-Mra Images
Loading...
Date
2024-01
Authors
Goni, Mohammad Raihan
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis introduces a deep learning approach to automatically segment cerebrovascular structures in magnetic resonance angiography (MRA) images. This study utilizes an approach that excels in segmenting the entire vessel structure while placing increased emphasis on accurately capturing small vessels (< 5 mm radius). The proposed method was evaluated on the MIDAS dataset, demonstrating its competitive performance with exceptional evaluation results.
Description
Keywords
Magnetic resonance imaging , MIDAS (Computer system)